© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58187
    Prev
    Next
    INDEX
    Explanations

    live broadcast reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     зимние
    -0.86
     новое
    -0.82
    inna
    -0.74
     Coc
    -0.74
    inkgo
    -0.73
    ಶ
    -0.73
    流水
    -0.70
     ADVERTISING
    -0.69
     coc
    -0.69
     mavi
    -0.68
    POSITIVE LOGITS
     actuality
    1.11
     live
    1.05
    PKG
    1.03
     interviews
    1.02
     SOT
    0.96
     VT
    0.95
     Packages
    0.93
    SOT
    0.90
     remote
    0.90
     piece
    0.89
    Activations Density 0.034%

    No Known Activations